Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance
This paper investigates the Contention Window (CW) optimization problem in multi-agent scenarios, where the fully cooperative among mobile stations is considered. A partially observable environment is employed to model and analyze the CW optimization problem, and Smart Exponential-Threshold-Linear w...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-10-01
|
Series: | ICT Express |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2405959522001060 |
_version_ | 1797653953067876352 |
---|---|
author | Chih-Heng Ke Lia Astuti |
author_facet | Chih-Heng Ke Lia Astuti |
author_sort | Chih-Heng Ke |
collection | DOAJ |
description | This paper investigates the Contention Window (CW) optimization problem in multi-agent scenarios, where the fully cooperative among mobile stations is considered. A partially observable environment is employed to model and analyze the CW optimization problem, and Smart Exponential-Threshold-Linear with Deep Q-learning Network (SETL-DQN) Multi-Agent (MA) algorithm is proposed to obtain the optimal system throughput through the CW Threshold optimization. In the determined scenarios, SETL-DQN(MA) can effectively cope with the mutual interaction among mobile stations. The simulation results show that our proposed method is superior from both static and dynamic scenarios and has the highest optimum packet transmission efficiency. |
first_indexed | 2024-03-11T16:51:17Z |
format | Article |
id | doaj.art-5211e7c816a14432964f2eac74fc13ce |
institution | Directory Open Access Journal |
issn | 2405-9595 |
language | English |
last_indexed | 2024-03-11T16:51:17Z |
publishDate | 2023-10-01 |
publisher | Elsevier |
record_format | Article |
series | ICT Express |
spelling | doaj.art-5211e7c816a14432964f2eac74fc13ce2023-10-21T04:22:55ZengElsevierICT Express2405-95952023-10-0195776782Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performanceChih-Heng Ke0Lia Astuti1Department of Computer Science and Information Engineering, National Quemoy University, Kinmen, 892, TaiwanMaster Program of Information Technology and Applications, National Quemoy University, Kinmen, 892, Taiwan; Corresponding author.This paper investigates the Contention Window (CW) optimization problem in multi-agent scenarios, where the fully cooperative among mobile stations is considered. A partially observable environment is employed to model and analyze the CW optimization problem, and Smart Exponential-Threshold-Linear with Deep Q-learning Network (SETL-DQN) Multi-Agent (MA) algorithm is proposed to obtain the optimal system throughput through the CW Threshold optimization. In the determined scenarios, SETL-DQN(MA) can effectively cope with the mutual interaction among mobile stations. The simulation results show that our proposed method is superior from both static and dynamic scenarios and has the highest optimum packet transmission efficiency.http://www.sciencedirect.com/science/article/pii/S2405959522001060CW optimizationCW thresholdSETL-DQN multi-agentSystem throughput |
spellingShingle | Chih-Heng Ke Lia Astuti Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance ICT Express CW optimization CW threshold SETL-DQN multi-agent System throughput |
title | Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance |
title_full | Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance |
title_fullStr | Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance |
title_full_unstemmed | Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance |
title_short | Applying multi-agent deep reinforcement learning for contention window optimization to enhance wireless network performance |
title_sort | applying multi agent deep reinforcement learning for contention window optimization to enhance wireless network performance |
topic | CW optimization CW threshold SETL-DQN multi-agent System throughput |
url | http://www.sciencedirect.com/science/article/pii/S2405959522001060 |
work_keys_str_mv | AT chihhengke applyingmultiagentdeepreinforcementlearningforcontentionwindowoptimizationtoenhancewirelessnetworkperformance AT liaastuti applyingmultiagentdeepreinforcementlearningforcontentionwindowoptimizationtoenhancewirelessnetworkperformance |